© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23892
    Prev
    Next
    INDEX
    Explanations

    accuracy and precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    éĦĦ
    -0.09
    仲
    -0.09
    æ¯Ļ
    -0.09
    èģĴ
    -0.09
     RESERVED
    -0.09
    caling
    -0.09
    çIJĩ
    -0.08
    adle
    -0.08
    æ£Ģ
    -0.08
    POSITIVE LOGITS
    åĩĨç¡®
    0.32
    åĩĨç¡®æĢ§
    0.29
     accuracy
    0.29
     accurate
    0.27
    accuracy
    0.25
    精确
    0.25
     Accuracy
    0.24
     accur
    0.24
    accur
    0.24
    Accuracy
    0.24
    Activations Density 0.084%

    No Known Activations